vectorize
Vectorize is a vector database that runs at the edge, letting you store high-dimensional embeddings and perform similarity queries for RAG pipelines, semantic search, and recommendation systems. Create indexes with preset dimensions or custom configurations, then insert, upsert, query, and delete vectors through a simple API. Integrates seamlessly with Workers AI for generating embeddings.
Vectorize stores and queries vector embeddings at the edge for RAG pipelines, semantic search, and similarity matching.
AI-generated summary based on this skill's SKILL.md
Install
null-shot/cloudflare-skills/vectorize · repository language: TypeScript
git clone https://github.com/null-shot/cloudflare-skills
cp -r cloudflare-skills/vectorize ~/.claude/skills/vectorizenpx skillfed install null-shot/cloudflare-skills/vectorizeFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is Vectorize and how does it store embeddings?
Vectorize is a vector database that runs at the edge, letting you store high-dimensional embeddings and perform similarity queries for RAG pipelines, semantic search, and recommendation systems. You can create indexes with preset dimensions or custom configurations, then insert, upsert, query, and delete vectors through a simple API.
Can I use Vectorize for a RAG pipeline vector storage?
Yes. Vectorize is designed to support RAG (Retrieval Augmented Generation) pipelines by storing embeddings and enabling fast similarity queries. You create indexes, insert your embeddings, and query them to retrieve relevant context for your language models.
How does Vectorize integrate with Workers AI embeddings?
Vectorize integrates seamlessly with Workers AI for generating embeddings. You can use Workers AI to create embeddings from your content, then store those embeddings in Vectorize indexes and perform similarity searches across them.
What can I build with Vectorize for semantic search?
Vectorize enables semantic search implementation without keyword matching by storing embeddings and performing similarity queries. You can build recommendation systems using embedding similarity, find duplicate or similar content using vectors, and implement nearest neighbor search at the edge.
How do I create and manage indexes in Vectorize?
Vectorize lets you create indexes with preset dimensions or custom configurations. Once created, you can insert, upsert, query, and delete vectors through a simple API. This gives you full control over your vector storage and retrieval operations.
Is Vectorize suitable for edge computing applications?
Yes. Vectorize runs at the edge, making it ideal for low-latency semantic search and similarity matching without sending data to centralized servers. This edge-native design supports high-dimensional vector search and real-time recommendation systems.
SKILL.md
rendered from the published skill — quoted content, verbatim
Cloudflare Vectorize
Store and query high-dimensional vector embeddings at the edge for RAG (Retrieval Augmented Generation), semantic search, and similarity matching.
FIRST: Create Index
# Create with preset (auto-configures dimensions and metric)
wrangler vectorize create my-index --preset @cf/baai/bge-base-en-v1.5
# Or create with explicit dimensions
wrangler vectorize create my-index --dimensions 768 --metric cosine
# List indexes
wrangler vectorize list
Add to wrangler.jsonc:
{
"vectorize": [
{ "binding": "SEARCH_INDEX", "index_name": "my-index" }
]
}
When to Use
| Use Case | Description |
|---|---|
| RAG Pipelines | Store document embeddings for context retrieval with LLMs |
| Semantic Search | Find similar content by meaning, not keywords |
| Recommendation Systems | Match users/items based on embedding similarity |
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 5 files
vectorize/SKILL.md
vectorize/references/indexing.md
vectorize/references/limits.md
vectorize/references/querying.md
vectorize/references/testing.md